Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4293 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.5321. Min Act: -0.1700
Data Index: 1569242 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.4071. Min Act: -0.1700
Data Index: 386468 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2821. Min Act: -0.1700
Data Index: 7105318 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2821. Min Act: -0.1700
Data Index: 4771098 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2821. Min Act: -0.1700
Data Index: 7885860 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2509. Min Act: -0.1700
Data Index: 5732799 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2196. Min Act: -0.1700
Data Index: 7149719 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.1884. Min Act: -0.1700
Data Index: 4799305 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.1884. Min Act: -0.1700
Data Index: 1520169 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.1884. Min Act: -0.1700
Data Index: 8361107 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.1571. Min Act: -0.1700
Data Index: 1869623 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.1571. Min Act: -0.1700
Data Index: 5398089 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.1259. Min Act: -0.1700
Data Index: 5390982 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.0634. Min Act: -0.1700
Data Index: 7162356 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.0634. Min Act: -0.1700
Data Index: 6972653 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.0321. Min Act: -0.1700
Data Index: 4562695 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.0321. Min Act: -0.1700
Data Index: 3402663 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.0009. Min Act: -0.1700
Data Index: 7956806 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5321. Min Range: -5.5321
Max Act: 4.9696. Min Act: -0.1700
Data Index: 1318744 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5321. Min Range: -5.5321
Max Act: 4.9696. Min Act: -0.1700
Data Index: 9360 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19